agentleFS
Sign inStart free
VuDZVuDZ/RoslynMcpServer/.cursor/rules/roslyn-mcp-version-bump.mdc

RoslynMcpServer / rules

Cursor rule8 starsChanged 45 days agoMITView on GitHub

Auto-bump Version after successful MCP self-build and reload

The file

We split this roslyn-mcp-version-bump.mdc into the rules it gives an agent

5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When changing RoslynMcpServer itself and verifying with this same MCP (build/test/run via MCP tools, then use the new binary):

    line 8
  2. Very specific:

    After a successful run_dotnet_build / dotnet test (and before or with dotnet publish + MCP reload):

    line 12
  3. Very specific:

    Do not leave shippable behavior changes at the old version — agents check get_mcp_server_info against the number in csproj/docs.

    line 15
  4. Very specific:

    Update CHANGELOG.md when user-visible tools/behavior change.

    line 26
  5. Very specific:

    Prefer MCP run_dotnet_build / run_dotnet_test / run_dotnet_run on this repo’s workspace — same as app repos.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
roslyn-mcp-version-bump.mdc
---
description: Auto-bump Version after successful MCP self-build and reload
alwaysApply: true
---

# Auto version bump (this MCP server)

When changing **RoslynMcpServer itself** and verifying with **this same MCP** (build/test/run via MCP tools, then use the new binary):

## When to bump

After a **successful** `run_dotnet_build` / `dotnet test` (and before or with `dotnet publish` + MCP reload):

1. Bump **patch** in `RoslynMcpServer.csproj`: `Version`, `AssemblyVersion`, `FileVersion` together (e.g. `1.0.14` → `1.0.15`, `1.0.14.0` → `1.0.15.0`).
2. Do **not** leave shippable behavior changes at the old version — agents check `get_mcp_server_info` against the number in csproj/docs.
3. Skip bump only for pure docs/typos/rules with **no** code or tool-behavior change.

## SemVer in this repo

- **Patch** (`1.0.x`): fixes, tool UX, parsers, path resolve, logging — default for almost every ship.
- **Minor** (`1.x.0`): new MCP tools or clearly additive public capabilities.
- There is no `PackageVersion`: the product is not a NuGet package. Do not add one.

## After bump

1. Update `CHANGELOG.md` when user-visible tools/behavior change. README already links to it; update Reference there when the tool catalog changes.
2. Sync `AGENTS.md.sample` / expected version hints (`get_mcp_server_info` → new version).
3. Publish (`publish-and-verify.ps1` or `dotnet publish … -r win-x64`), reload MCP host, confirm **`get_mcp_server_info`** shows the new version.

## Dogfooding

Prefer MCP `run_dotnet_build` / `run_dotnet_test` / `run_dotnet_run` on this repo’s workspace — same as app repos. Shell `dotnet` only if MCP is unavailable or for publish/reload scripts that are outside tool coverage.

`publish-and-verify.ps1` stops leftover `RoslynMcpServer.exe` under this repo/publish (Cursor often keeps MCP alive after disconnect and locks publish DLLs). Pass `-SkipKill` to disable. Then reload MCP and confirm `get_mcp_server_info`.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free